Decentralized gradient descent tracks the minimizer of temporally weighted streaming objectives, achieving O(1/t) fixed-point tracking under uniform weights and a non-vanishing floor under exponential discounting, plus a heterogeneity-induced bias floor.
Distributed subgradient methods for multi- agent optimization,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SP 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Decentralized Time-Varying Optimization for Streaming Data via Temporal Weighting
Decentralized gradient descent tracks the minimizer of temporally weighted streaming objectives, achieving O(1/t) fixed-point tracking under uniform weights and a non-vanishing floor under exponential discounting, plus a heterogeneity-induced bias floor.